AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference

• URL: http://arxiv.org/abs/2605.29535v1
• Date: Thu, 28 May 2026 07:49:45 GMT
• Title: AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference
• Abstract summary: Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens.<n>We propose and empirically evaluate AsymVLM, which applies aggressive pruning to vision tokens before prefill.<n>Our experiments indicate that AsymVLM achieves the highest FLOPs savings (up to 54%) among state-of-the-art methods.
• Score: 7.243327337529763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally different properties: vision tokens are spatially redundant and dominate prefill, while text tokens are causally dependent and accumulate during decoding. Based on this asymmetry, we propose and empirically evaluate AsymVLM, which applies aggressive pruning to vision tokens before prefill using a learned importance scorer with per-sample adaptive budgeting, and temporal threshold-based eviction to text tokens only when they exceed a fixed budget. Our experiments indicate that AsymVLM achieves the highest FLOPs savings (up to 54%) among state-of-the-art methods while outperforming existing approaches by 2--3% on document and chart understanding tasks where visual information is spatially localized and query-specific, and maintaining competitive accuracy on holistic benchmarks. In text-dominated scenarios, our eviction strategy substantially outperforms standard LLM cache compression methods by adapting to the short-context nature of VLM.

Related papers

• When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs [13.67813408204418]
  Visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs.<n>Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression.<n>We present SIEVE, a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complementary tokens.
  arXiv  Detail & Related papers  (2026-08-11T05:04:33Z)
• IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning [27.75049214892312]
  Large Vision-Language Models (LVLMs) achieve impressive performance across multiple tasks.<n>A significant challenge, however, is their prohibitive inference cost when processing high-resolution visual inputs.<n>We propose textbfIVC-Prune, a training-free, prompt-aware pruning strategy that retains both IVC tokens and semantically relevant foreground tokens.
  arXiv  Detail & Related papers  (2026-02-03T03:39:31Z)
• Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning [82.39668822222386]
  Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM)<n>We propose $textNwa$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity.<n>Experiments demonstrate that $textNwa$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%)
  arXiv  Detail & Related papers  (2026-02-03T00:51:03Z)
• AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs [29.68162972167947]
  We propose an object-level token merging strategy for Adaptive Token compression.<n>Our approach averagely, utilizes only 10% tokens while achieving almost 96% of the vanilla model's performance.
  arXiv  Detail & Related papers  (2025-11-18T06:12:15Z)
• ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models [7.7352936204066]
  We propose a novel, zero-shot method to model visual token pruning as a balance between task relevance and information diversity.<n>Our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss.<n>These gains are accompanied by significant reductions in GPU memory footprint and inference latency.
  arXiv  Detail & Related papers  (2025-10-20T06:18:47Z)
• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models [75.88232735646018]
  Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos.<n>Existing methods attempt to prune redundant vision tokens, revealing substantial redundancy in visual representations.<n>We propose CoViPAL, a layer-wise contextualized visual token pruning method that employs a Plug-and-Play Pruning Module (PPM) to predict and remove redundant vision tokens before they are processed by the LVLM.
  arXiv  Detail & Related papers  (2025-08-24T07:47:00Z)
• Revisit What You See: Disclose Language Prior in Vision Tokens for LVLM Decoding [6.612630497074871]
  Large Vision-Language Models (LVLMs) achieve strong performance across multimodal tasks by integrating visual perception with language understanding.<n>We propose ReVisiT, a training-free decoding method that references vision tokens to guide text generation.
  arXiv  Detail & Related papers  (2025-06-11T08:46:55Z)
• Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs [51.93737995405164]
  Large Vision-Language Models (LVLMs) are susceptible to hallucinations.<n>We introduce a novel Conditional Pointwise Mutual Information (C-PMI) calibrated decoding strategy.<n>We show that the proposed method significantly reduces hallucinations in LVLMs while preserving decoding efficiency.
  arXiv  Detail & Related papers  (2025-05-26T08:36:10Z)
• Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models [85.51753014478315]
  We introduce AdaptPrune, a novel plug-and-play training-free pruning method.<n>It builds on conventional attention-based pruning by integrating spatial distance and token similarity with an adaptive NMS approach.<n>Our approach ensures a comprehensive evaluation of token importance and substantially refines the pruning decisions.
  arXiv  Detail & Related papers  (2025-03-11T03:58:17Z)
• Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction [62.8375542401319]
  Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone.<n>The number of vision tokens increases quadratically as the image resolutions, leading to huge computational costs.<n>We propose a greedy search algorithm (G-Search) to find the least number of vision tokens to keep at each layer from the shallow to the deep.
  arXiv  Detail & Related papers  (2024-11-30T18:54:32Z)
• Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks.<n>To reduce inference costs, one can either downsize the Large Language Models (LLMs) or reduce the number of input tokens needed to represent the image.<n>We take the first steps toward designing token compression algorithms tailored for high-compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.